18582520. METHODS FOR PERFORMING PROCESSING-IN-MEMORY OPERATIONS, AND RELATED SYSTEMS simplified abstract (Micron Technology, Inc.)
Contents
METHODS FOR PERFORMING PROCESSING-IN-MEMORY OPERATIONS, AND RELATED SYSTEMS
Organization Name
Inventor(s)
Dmitri Yudanov of Cordova CA (US)
Sean S. Eilert of Penryn CA (US)
Sivagnanam Parthasarathy of Carlsbad CA (US)
Shivasankar Gunasekaran of Folsom CA (US)
Ameen D. Akel of Rancho Cordova CA (US)
METHODS FOR PERFORMING PROCESSING-IN-MEMORY OPERATIONS, AND RELATED SYSTEMS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18582520 titled 'METHODS FOR PERFORMING PROCESSING-IN-MEMORY OPERATIONS, AND RELATED SYSTEMS
Simplified Explanation: The patent application describes methods, apparatuses, and systems for processing data in or near memory, allowing for operations to be performed on data without the need for a separate processing unit.
Key Features and Innovation:
- Strings of bits, such as vectors, can be fetched and processed within the logic of a memory device.
- Arithmetic operations can be performed on numbers stored in a bit-parallel way during a single sequence of clock cycles.
- Arithmetic operations can be performed in a single pass without the need for intermediate storage of numbers.
- Vectors can be fetched from bit lines and processed.
- Registers in a memory array can be used to store results or ancillary bits that facilitate arithmetic operations.
- Circuitry near the memory array can employ XOR or AND logic to operate on the data.
Potential Applications: This technology could be applied in high-performance computing, data processing, and artificial intelligence systems.
Problems Solved: This technology addresses the need for efficient data processing and arithmetic operations without the reliance on separate processing units.
Benefits:
- Faster data processing
- Reduced energy consumption
- Simplified system architecture
Commercial Applications: Potential commercial applications include data centers, supercomputing facilities, and AI research labs.
Prior Art: Prior art related to this technology may include research on in-memory computing, parallel processing, and logic operations within memory devices.
Frequently Updated Research: Ongoing research in the field of in-memory processing and parallel computing may provide further insights into the optimization of these techniques.
Questions about in-memory processing: 1. How does in-memory processing differ from traditional processing methods? 2. What are the potential limitations of in-memory processing in real-world applications?
Original Abstract Submitted
Methods, apparatuses, and systems for in-or near-memory processing are described. Strings of bits (e.g., vectors) may be fetched and processed in logic of a memory device without involving a separate processing unit. Operations (e.g., arithmetic operations) may be performed on numbers stored in a bit-parallel way during a single sequence of clock cycles. Arithmetic may thus be performed in a single pass as numbers are bits of two or more strings of bits are fetched and without intermediate storage of the numbers. Vectors may be fetched (e.g., identified, transmitted, received) from one or more bit lines. Registers of a memory array may be used to write (e.g., store or temporarily store) results or ancillary bits (e.g., carry bits or carry flags) that facilitate arithmetic operations. Circuitry near, adjacent, or under the memory array may employ XOR or AND (or other) logic to fetch, organize, or operate on the data.
